RESUMEN
With the introduction of spectral-domain optical coherence tomography (OCT), resulting in a significant increase in acquisition speed, the fast and accurate segmentation of 3-D OCT scans has become evermore important. This paper presents a novel probabilistic approach, that models the appearance of retinal layers as well as the global shape variations of layer boundaries. Given an OCT scan, the full posterior distribution over segmentations is approximately inferred using a variational method enabling efficient probabilistic inference in terms of computationally tractable model components: Segmenting a full 3-D volume takes around a minute. Accurate segmentations demonstrate the benefit of using global shape regularization: We segmented 35 fovea-centered 3-D volumes with an average unsigned error of 2.46 ± 0.22 µm as well as 80 normal and 66 glaucomatous 2-D circular scans with errors of 2.92 ± 0.5 µm and 4.09 ± 0.98 µm respectively. Furthermore, we utilized the inferred posterior distribution to rate the quality of the segmentation, point out potentially erroneous regions and discriminate normal from pathological scans. No pre- or postprocessing was required and we used the same set of parameters for all data sets, underlining the robustness and out-of-the-box nature of our approach.
Asunto(s)
Glaucoma/patología , Interpretación de Imagen Asistida por Computador/métodos , Imagenología Tridimensional/métodos , Reconocimiento de Normas Patrones Automatizadas/métodos , Retina/patología , Retinoscopía/métodos , Tomografía de Coherencia Óptica/métodos , Algoritmos , Inteligencia Artificial , Simulación por Computador , Interpretación Estadística de Datos , Femenino , Humanos , Aumento de la Imagen/métodos , Masculino , Modelos Estadísticos , Reproducibilidad de los Resultados , Sensibilidad y EspecificidadRESUMEN
We present a probabilistic approach to the segmentation of OCT scans of retinal tissue. By combining discrete exact inference and a global shape prior, accurate segmentations are computed that preserve the physiological order of intra-retinal layers. A major part of the computations can be performed in parallel. The evaluation reveals robustness against speckle noise, shadowing caused by blood vessels, and other scan artifacts.
Asunto(s)
Procesamiento de Imagen Asistido por Computador/métodos , Retina/patología , Tomografía de Coherencia Óptica/métodos , Algoritmos , Diagnóstico por Imagen/métodos , Humanos , Imagenología Tridimensional , Modelos Estadísticos , Análisis de Componente Principal , Probabilidad , Reproducibilidad de los Resultados , Programas InformáticosRESUMEN
Screening large libraries of chemical compounds against a biological target, typically a receptor or an enzyme, is a crucial step in the process of drug discovery. Virtual screening (VS) can be seen as a ranking problem which prefers as many actives as possible at the top of the ranking. As a standard, current Quantitative Structure-Activity Relationship (QSAR) models apply regression methods to predict the level of activity for each molecule and then sort them to establish the ranking. In this paper, we propose a top-k ranking algorithm (StructRank) based on Support Vector Machines to solve the early recognition problem directly. Empirically, we show that our ranking approach outperforms not only regression methods but another ranking approach recently proposed for QSAR ranking, RankSVM, in terms of actives found.
Asunto(s)
Evaluación Preclínica de Medicamentos/métodos , Interfaz Usuario-Computador , Inteligencia Artificial , Inhibidores Enzimáticos/química , Inhibidores Enzimáticos/farmacología , Ligandos , Análisis de Regresión , Relación Estructura-Actividad , Factores de TiempoRESUMEN
In the present work we develop a predictive QSAR model for the blockade of the hERG channel. Additionally, this specific end point is used as a test scenario to develop and evaluate several techniques for fusing predictions from multiple regression models. hERG inhibition models which are presented here are based on a combined data set of roughly 550 proprietary and 110 public domain compounds. Models are built using various statistical learning techniques and different sets of molecular descriptors. Single Support Vector Regression, Gaussian Process, or Random Forest models achieve root mean-squared errors of roughly 0.6 log units as determined from leave-group-out cross-validation. An analysis of the evaluation strategy on the performance estimates shows that standard leave-group-out cross-validation yields overly optimistic results. As an alternative, a clustered cross-validation scheme is introduced to obtain a more realistic estimate of the model performance. The evaluation of several techniques to combine multiple prediction models shows that the root mean squared error as determined from clustered cross-validation can be reduced from 0.73 +/- 0.01 to 0.57 +/- 0.01 using a local bias correction strategy.